integration-tests

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple shell commands via pnpm to manage a local development environment. This includes starting a background registry process (pnpm local-npm:start), building the project (pnpm build), and running integration tests (pnpm test:integration).
  • [EXTERNAL_DOWNLOADS]: The skill uses pnpm i to install project dependencies. While this fetches packages from external registries, it is a standard and expected operation for development-oriented skills.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting and following instructions from a local file (integration-tests/README.md) to guide its troubleshooting behavior.
  • Ingestion points: Reads content from integration-tests/README.md when troubleshooting failures.
  • Boundary markers: None identified in the instructions for separating file content from system instructions.
  • Capability inventory: The skill has the capability to execute shell commands and manage system processes.
  • Sanitization: No sanitization or validation of the README content is performed before the agent processes it for recovery steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 04:52 PM
Security Audit — agent-trust-hub — integration-tests